liaozhaorun/NewStock
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

1、策略更新

Browse Source 
2、新增qmt
This commit is contained in:
liaozhaorun
2025-11-29 00:23:12 +08:00
parent 0a942f92d1
commit c9b61db5b7
47 changed files with 97116 additions and 8867 deletions
Download Patch File Download Diff File Expand all files Collapse all files

158
main/train/Classify2_load_model.ipynb
View File

@@ -68,28 +68,56 @@
"name": "stdout",
"output_type": "stream",
"text": [
"daily data\n"
]
},
{
"ename": "KeyboardInterrupt",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[31m---------------------------------------------------------------------------\u001b[39m",
"\u001b[31mKeyboardInterrupt\u001b[39m Traceback (most recent call last)",
"\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[3]\u001b[39m\u001b[32m, line 4\u001b[39m\n\u001b[32m 1\u001b[39m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mmain\u001b[39;00m\u001b[34;01m.\u001b[39;00m\u001b[34;01mutils\u001b[39;00m\u001b[34;01m.\u001b[39;00m\u001b[34;01mutils\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m read_and_merge_h5_data\n\u001b[32m 3\u001b[39m \u001b[38;5;28mprint\u001b[39m(\u001b[33m'\u001b[39m\u001b[33mdaily data\u001b[39m\u001b[33m'\u001b[39m)\n\u001b[32m----> \u001b[39m\u001b[32m4\u001b[39m df = \u001b[43mread_and_merge_h5_data\u001b[49m\u001b[43m(\u001b[49m\u001b[33;43m'\u001b[39;49m\u001b[33;43m/mnt/d/PyProject/NewStock/data/daily_data.h5\u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkey\u001b[49m\u001b[43m=\u001b[49m\u001b[33;43m'\u001b[39;49m\u001b[33;43mdaily_data\u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[32m 5\u001b[39m \u001b[43m \u001b[49m\u001b[43mcolumns\u001b[49m\u001b[43m=\u001b[49m\u001b[43m[\u001b[49m\u001b[33;43m'\u001b[39;49m\u001b[33;43mts_code\u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[33;43m'\u001b[39;49m\u001b[33;43mtrade_date\u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[33;43m'\u001b[39;49m\u001b[33;43mopen\u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[33;43m'\u001b[39;49m\u001b[33;43mclose\u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[33;43m'\u001b[39;49m\u001b[33;43mhigh\u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[33;43m'\u001b[39;49m\u001b[33;43mlow\u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[33;43m'\u001b[39;49m\u001b[33;43mvol\u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[33;43m'\u001b[39;49m\u001b[33;43mamount\u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[33;43m'\u001b[39;49m\u001b[33;43mpct_chg\u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 6\u001b[39m \u001b[43m \u001b[49m\u001b[43mdf\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\n\u001b[32m 8\u001b[39m \u001b[38;5;28mprint\u001b[39m(\u001b[33m'\u001b[39m\u001b[33mdaily basic\u001b[39m\u001b[33m'\u001b[39m)\n\u001b[32m 9\u001b[39m df = read_and_merge_h5_data(\u001b[33m'\u001b[39m\u001b[33m/mnt/d/PyProject/NewStock/data/daily_basic.h5\u001b[39m\u001b[33m'\u001b[39m, key=\u001b[33m'\u001b[39m\u001b[33mdaily_basic\u001b[39m\u001b[33m'\u001b[39m,\n\u001b[32m 10\u001b[39m columns=[\u001b[33m'\u001b[39m\u001b[33mts_code\u001b[39m\u001b[33m'\u001b[39m, \u001b[33m'\u001b[39m\u001b[33mtrade_date\u001b[39m\u001b[33m'\u001b[39m, \u001b[33m'\u001b[39m\u001b[33mturnover_rate\u001b[39m\u001b[33m'\u001b[39m, \u001b[33m'\u001b[39m\u001b[33mpe_ttm\u001b[39m\u001b[33m'\u001b[39m, \u001b[33m'\u001b[39m\u001b[33mcirc_mv\u001b[39m\u001b[33m'\u001b[39m, \u001b[33m'\u001b[39m\u001b[33mtotal_mv\u001b[39m\u001b[33m'\u001b[39m, \u001b[33m'\u001b[39m\u001b[33mvolume_ratio\u001b[39m\u001b[33m'\u001b[39m,\n\u001b[32m 11\u001b[39m \u001b[33m'\u001b[39m\u001b[33mis_st\u001b[39m\u001b[33m'\u001b[39m], df=df, join=\u001b[33m'\u001b[39m\u001b[33minner\u001b[39m\u001b[33m'\u001b[39m)\n",
"\u001b[36mFile \u001b[39m\u001b[32m/mnt/d/PyProject/NewStock/main/utils/utils.py:14\u001b[39m, in \u001b[36mread_and_merge_h5_data\u001b[39m\u001b[34m(h5_filename, key, columns, df, join, on, prefix)\u001b[39m\n\u001b[32m 11\u001b[39m processed_columns.append(col)\n\u001b[32m 13\u001b[39m \u001b[38;5;66;03m# 从 HDF5 文件读取数据，选择需要的列\u001b[39;00m\n\u001b[32m---> \u001b[39m\u001b[32m14\u001b[39m data = \u001b[43mpd\u001b[49m\u001b[43m.\u001b[49m\u001b[43mread_hdf\u001b[49m\u001b[43m(\u001b[49m\u001b[43mh5_filename\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkey\u001b[49m\u001b[43m=\u001b[49m\u001b[43mkey\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcolumns\u001b[49m\u001b[43m=\u001b[49m\u001b[43mprocessed_columns\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 16\u001b[39m \u001b[38;5;66;03m# 修改列名，如果列名以前有 _，加上 _\u001b[39;00m\n\u001b[32m 17\u001b[39m \u001b[38;5;28;01mfor\u001b[39;00m col \u001b[38;5;129;01min\u001b[39;00m data.columns:\n",
"\u001b[36mFile \u001b[39m\u001b[32m~/miniconda3/envs/stock/lib/python3.13/site-packages/pandas/io/pytables.py:452\u001b[39m, in \u001b[36mread_hdf\u001b[39m\u001b[34m(path_or_buf, key, mode, errors, where, start, stop, columns, iterator, chunksize, **kwargs)\u001b[39m\n\u001b[32m 447\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[32m 448\u001b[39m \u001b[33m\"\u001b[39m\u001b[33mkey must be provided when HDF5 \u001b[39m\u001b[33m\"\u001b[39m\n\u001b[32m 449\u001b[39m \u001b[33m\"\u001b[39m\u001b[33mfile contains multiple datasets.\u001b[39m\u001b[33m\"\u001b[39m\n\u001b[32m 450\u001b[39m )\n\u001b[32m 451\u001b[39m key = candidate_only_group._v_pathname\n\u001b[32m--> \u001b[39m\u001b[32m452\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mstore\u001b[49m\u001b[43m.\u001b[49m\u001b[43mselect\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m 453\u001b[39m \u001b[43m \u001b[49m\u001b[43mkey\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 454\u001b[39m \u001b[43m \u001b[49m\u001b[43mwhere\u001b[49m\u001b[43m=\u001b[49m\u001b[43mwhere\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 455\u001b[39m \u001b[43m \u001b[49m\u001b[43mstart\u001b[49m\u001b[43m=\u001b[49m\u001b[43mstart\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 456\u001b[39m \u001b[43m \u001b[49m\u001b[43mstop\u001b[49m\u001b[43m=\u001b[49m\u001b[43mstop\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 457\u001b[39m \u001b[43m \u001b[49m\u001b[43mcolumns\u001b[49m\u001b[43m=\u001b[49m\u001b[43mcolumns\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 458\u001b[39m \u001b[43m \u001b[49m\u001b[43miterator\u001b[49m\u001b[43m=\u001b[49m\u001b[43miterator\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 459\u001b[39m \u001b[43m \u001b[49m\u001b[43mchunksize\u001b[49m\u001b[43m=\u001b[49m\u001b[43mchunksize\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 460\u001b[39m \u001b[43m \u001b[49m\u001b[43mauto_close\u001b[49m\u001b[43m=\u001b[49m\u001b[43mauto_close\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 461\u001b[39m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 462\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m (\u001b[38;5;167;01mValueError\u001b[39;00m, \u001b[38;5;167;01mTypeError\u001b[39;00m, \u001b[38;5;167;01mLookupError\u001b[39;00m):\n\u001b[32m 463\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(path_or_buf, HDFStore):\n\u001b[32m 464\u001b[39m \u001b[38;5;66;03m# if there is an error, close the store if we opened it.\u001b[39;00m\n",
"\u001b[36mFile \u001b[39m\u001b[32m~/miniconda3/envs/stock/lib/python3.13/site-packages/pandas/io/pytables.py:906\u001b[39m, in \u001b[36mHDFStore.select\u001b[39m\u001b[34m(self, key, where, start, stop, columns, iterator, chunksize, auto_close)\u001b[39m\n\u001b[32m 892\u001b[39m \u001b[38;5;66;03m# create the iterator\u001b[39;00m\n\u001b[32m 893\u001b[39m it = TableIterator(\n\u001b[32m 894\u001b[39m \u001b[38;5;28mself\u001b[39m,\n\u001b[32m 895\u001b[39m s,\n\u001b[32m (...)\u001b[39m\u001b[32m 903\u001b[39m auto_close=auto_close,\n\u001b[32m 904\u001b[39m )\n\u001b[32m--> \u001b[39m\u001b[32m906\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mit\u001b[49m\u001b[43m.\u001b[49m\u001b[43mget_result\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n",
"\u001b[36mFile \u001b[39m\u001b[32m~/miniconda3/envs/stock/lib/python3.13/site-packages/pandas/io/pytables.py:2029\u001b[39m, in \u001b[36mTableIterator.get_result\u001b[39m\u001b[34m(self, coordinates)\u001b[39m\n\u001b[32m 2026\u001b[39m where = \u001b[38;5;28mself\u001b[39m.where\n\u001b[32m 2028\u001b[39m \u001b[38;5;66;03m# directly return the result\u001b[39;00m\n\u001b[32m-> \u001b[39m\u001b[32m2029\u001b[39m results = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mstart\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mstop\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mwhere\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 2030\u001b[39m \u001b[38;5;28mself\u001b[39m.close()\n\u001b[32m 2031\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m results\n",
"\u001b[36mFile \u001b[39m\u001b[32m~/miniconda3/envs/stock/lib/python3.13/site-packages/pandas/io/pytables.py:890\u001b[39m, in \u001b[36mHDFStore.select.<locals>.func\u001b[39m\u001b[34m(_start, _stop, _where)\u001b[39m\n\u001b[32m 889\u001b[39m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34mfunc\u001b[39m(_start, _stop, _where):\n\u001b[32m--> \u001b[39m\u001b[32m890\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43ms\u001b[49m\u001b[43m.\u001b[49m\u001b[43mread\u001b[49m\u001b[43m(\u001b[49m\u001b[43mstart\u001b[49m\u001b[43m=\u001b[49m\u001b[43m_start\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstop\u001b[49m\u001b[43m=\u001b[49m\u001b[43m_stop\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mwhere\u001b[49m\u001b[43m=\u001b[49m\u001b[43m_where\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcolumns\u001b[49m\u001b[43m=\u001b[49m\u001b[43mcolumns\u001b[49m\u001b[43m)\u001b[49m\n",
"\u001b[36mFile \u001b[39m\u001b[32m~/miniconda3/envs/stock/lib/python3.13/site-packages/pandas/io/pytables.py:4631\u001b[39m, in \u001b[36mAppendableFrameTable.read\u001b[39m\u001b[34m(self, where, columns, start, stop)\u001b[39m\n\u001b[32m 4628\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28mself\u001b[39m.infer_axes():\n\u001b[32m 4629\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[32m-> \u001b[39m\u001b[32m4631\u001b[39m result = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_read_axes\u001b[49m\u001b[43m(\u001b[49m\u001b[43mwhere\u001b[49m\u001b[43m=\u001b[49m\u001b[43mwhere\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstart\u001b[49m\u001b[43m=\u001b[49m\u001b[43mstart\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstop\u001b[49m\u001b[43m=\u001b[49m\u001b[43mstop\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 4633\u001b[39m info = (\n\u001b[32m 4634\u001b[39m \u001b[38;5;28mself\u001b[39m.info.get(\u001b[38;5;28mself\u001b[39m.non_index_axes[\u001b[32m0\u001b[39m][\u001b[32m0\u001b[39m], {})\n\u001b[32m 4635\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(\u001b[38;5;28mself\u001b[39m.non_index_axes)\n\u001b[32m 4636\u001b[39m \u001b[38;5;28;01melse\u001b[39;00m {}\n\u001b[32m 4637\u001b[39m )\n\u001b[32m 4639\u001b[39m inds = [i \u001b[38;5;28;01mfor\u001b[39;00m i, ax \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28menumerate\u001b[39m(\u001b[38;5;28mself\u001b[39m.axes) \u001b[38;5;28;01mif\u001b[39;00m ax \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28mself\u001b[39m.index_axes[\u001b[32m0\u001b[39m]]\n",
"\u001b[36mFile \u001b[39m\u001b[32m~/miniconda3/envs/stock/lib/python3.13/site-packages/pandas/io/pytables.py:3818\u001b[39m, in \u001b[36mTable._read_axes\u001b[39m\u001b[34m(self, where, start, stop)\u001b[39m\n\u001b[32m 3816\u001b[39m \u001b[38;5;66;03m# create the selection\u001b[39;00m\n\u001b[32m 3817\u001b[39m selection = Selection(\u001b[38;5;28mself\u001b[39m, where=where, start=start, stop=stop)\n\u001b[32m-> \u001b[39m\u001b[32m3818\u001b[39m values = \u001b[43mselection\u001b[49m\u001b[43m.\u001b[49m\u001b[43mselect\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 3820\u001b[39m results = []\n\u001b[32m 3821\u001b[39m \u001b[38;5;66;03m# convert the data\u001b[39;00m\n",
"\u001b[36mFile \u001b[39m\u001b[32m~/miniconda3/envs/stock/lib/python3.13/site-packages/pandas/io/pytables.py:5397\u001b[39m, in \u001b[36mSelection.select\u001b[39m\u001b[34m(self)\u001b[39m\n\u001b[32m 5395\u001b[39m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28mself\u001b[39m.coordinates \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[32m 5396\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m.table.table.read_coordinates(\u001b[38;5;28mself\u001b[39m.coordinates)\n\u001b[32m-> \u001b[39m\u001b[32m5397\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mtable\u001b[49m\u001b[43m.\u001b[49m\u001b[43mtable\u001b[49m\u001b[43m.\u001b[49m\u001b[43mread\u001b[49m\u001b[43m(\u001b[49m\u001b[43mstart\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mstart\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstop\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mstop\u001b[49m\u001b[43m)\u001b[49m\n",
"\u001b[36mFile \u001b[39m\u001b[32m~/miniconda3/envs/stock/lib/python3.13/site-packages/tables/table.py:2083\u001b[39m, in \u001b[36mTable.read\u001b[39m\u001b[34m(self, start, stop, step, field, out)\u001b[39m\n\u001b[32m 2077\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m(msg)\n\u001b[32m 2079\u001b[39m start, stop, step = \u001b[38;5;28mself\u001b[39m._process_range(\n\u001b[32m 2080\u001b[39m start, stop, step, warn_negstep=\u001b[38;5;28;01mFalse\u001b[39;00m\n\u001b[32m 2081\u001b[39m )\n\u001b[32m-> \u001b[39m\u001b[32m2083\u001b[39m arr = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_read\u001b[49m\u001b[43m(\u001b[49m\u001b[43mstart\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstop\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstep\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfield\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mout\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 2084\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m internal_to_flavor(arr, \u001b[38;5;28mself\u001b[39m.flavor)\n",
"\u001b[36mFile \u001b[39m\u001b[32m~/miniconda3/envs/stock/lib/python3.13/site-packages/tables/table.py:1989\u001b[39m, in \u001b[36mTable._read\u001b[39m\u001b[34m(self, start, stop, step, field, out)\u001b[39m\n\u001b[32m 1985\u001b[39m \u001b[38;5;66;03m# Call the routine to fill-up the resulting array\u001b[39;00m\n\u001b[32m 1986\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m step == \u001b[32m1\u001b[39m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m field:\n\u001b[32m 1987\u001b[39m \u001b[38;5;66;03m# This optimization works three times faster than\u001b[39;00m\n\u001b[32m 1988\u001b[39m \u001b[38;5;66;03m# the row._fill_col method (up to 170 MB/s on a pentium IV @ 2GHz)\u001b[39;00m\n\u001b[32m-> \u001b[39m\u001b[32m1989\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_read_records\u001b[49m\u001b[43m(\u001b[49m\u001b[43mstart\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstop\u001b[49m\u001b[43m \u001b[49m\u001b[43m-\u001b[49m\u001b[43m \u001b[49m\u001b[43mstart\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mresult\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 1990\u001b[39m \u001b[38;5;66;03m# Warning!: _read_field_name should not be used until\u001b[39;00m\n\u001b[32m 1991\u001b[39m \u001b[38;5;66;03m# H5TBread_fields_name in tableextension will be finished\u001b[39;00m\n\u001b[32m 1992\u001b[39m \u001b[38;5;66;03m# F. Alted 2005/05/26\u001b[39;00m\n\u001b[32m 1993\u001b[39m \u001b[38;5;66;03m# XYX Ho implementem per a PyTables 2.0??\u001b[39;00m\n\u001b[32m 1994\u001b[39m \u001b[38;5;28;01melif\u001b[39;00m field \u001b[38;5;129;01mand\u001b[39;00m step > \u001b[32m15\u001b[39m \u001b[38;5;129;01mand\u001b[39;00m \u001b[32m0\u001b[39m:\n\u001b[32m 1995\u001b[39m \u001b[38;5;66;03m# For step>15, this seems to work always faster than row._fill_col.\u001b[39;00m\n",
"\u001b[31mKeyboardInterrupt\u001b[39m: "
"daily data\n",
"daily basic\n",
"inner merge on ['ts_code', 'trade_date']\n",
"stk limit\n",
"left merge on ['ts_code', 'trade_date']\n",
"money flow\n",
"left merge on ['ts_code', 'trade_date']\n",
"cyq perf\n",
"left merge on ['ts_code', 'trade_date']\n",
"<class 'pandas.core.frame.DataFrame'>\n",
"RangeIndex: 9315967 entries, 0 to 9315966\n",
"Data columns (total 33 columns):\n",
" # Column Dtype \n",
"--- ------ ----- \n",
" 0 ts_code object \n",
" 1 trade_date datetime64[ns]\n",
" 2 open float64 \n",
" 3 close float64 \n",
" 4 high float64 \n",
" 5 low float64 \n",
" 6 vol float64 \n",
" 7 amount float64 \n",
" 8 pct_chg float64 \n",
" 9 turnover_rate float64 \n",
" 10 pe_ttm float64 \n",
" 11 circ_mv float64 \n",
" 12 total_mv float64 \n",
" 13 volume_ratio float64 \n",
" 14 is_st bool \n",
" 15 up_limit float64 \n",
" 16 down_limit float64 \n",
" 17 buy_sm_vol float64 \n",
" 18 sell_sm_vol float64 \n",
" 19 buy_lg_vol float64 \n",
" 20 sell_lg_vol float64 \n",
" 21 buy_elg_vol float64 \n",
" 22 sell_elg_vol float64 \n",
" 23 net_mf_vol float64 \n",
" 24 his_low float64 \n",
" 25 his_high float64 \n",
" 26 cost_5pct float64 \n",
" 27 cost_15pct float64 \n",
" 28 cost_50pct float64 \n",
" 29 cost_85pct float64 \n",
" 30 cost_95pct float64 \n",
" 31 weight_avg float64 \n",
" 32 winner_rate float64 \n",
"dtypes: bool(1), datetime64[ns](1), float64(30), object(1)\n",
"memory usage: 2.2+ GB\n",
"None\n"
]
}
],
@@ -126,7 +154,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 4,
"id": "cac01788dac10678",
"metadata": {
"ExecuteTime": {
@@ -194,7 +222,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 5,
"id": "c4e9e1d31da6dba6",
"metadata": {
"ExecuteTime": {
@@ -294,7 +322,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 6,
"id": "a735bc02ceb4d872",
"metadata": {
"ExecuteTime": {
@@ -310,7 +338,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 7,
"id": "53f86ddc0677a6d7",
"metadata": {
"ExecuteTime": {
@@ -377,7 +405,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 8,
"id": "dbe2fd8021b9417f",
"metadata": {
"ExecuteTime": {
@@ -405,7 +433,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 9,
"id": "85c3e3d0235ffffa",
"metadata": {
"ExecuteTime": {
@@ -437,7 +465,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 10,
"id": "92d84ce15a562ec6",
"metadata": {
"ExecuteTime": {
@@ -572,10 +600,10 @@
"Calculating cs_rank_size...\n",
"Finished cs_rank_size.\n",
"<class 'pandas.core.frame.DataFrame'>\n",
"RangeIndex: 4819708 entries, 0 to 4819707\n",
"RangeIndex: 4910010 entries, 0 to 4910009\n",
"Columns: 181 entries, ts_code to cs_rank_size\n",
"dtypes: bool(10), datetime64[ns](1), float64(165), int64(3), object(2)\n",
"memory usage: 6.2+ GB\n",
"memory usage: 6.3+ GB\n",
"None\n",
"['ts_code', 'trade_date', 'open', 'close', 'high', 'low', 'vol', 'amount', 'pct_chg', 'turnover_rate', 'pe_ttm', 'circ_mv', 'total_mv', 'volume_ratio', 'is_st', 'up_limit', 'down_limit', 'buy_sm_vol', 'sell_sm_vol', 'buy_lg_vol', 'sell_lg_vol', 'buy_elg_vol', 'sell_elg_vol', 'net_mf_vol', 'his_low', 'his_high', 'cost_5pct', 'cost_15pct', 'cost_50pct', 'cost_85pct', 'cost_95pct', 'weight_avg', 'winner_rate', 'cat_l2_code', 'undist_profit_ps', 'ocfps', 'roa', 'roe', 'AR', 'BR', 'AR_BR', 'log_circ_mv', 'cashflow_to_ev_factor', 'book_to_price_ratio', 'turnover_rate_mean_5', 'variance_20', 'bbi_ratio_factor', 'daily_deviation', 'lg_elg_net_buy_vol', 'flow_lg_elg_intensity', 'sm_net_buy_vol', 'flow_divergence_diff', 'flow_divergence_ratio', 'total_buy_vol', 'lg_elg_buy_prop', 'flow_struct_buy_change', 'lg_elg_net_buy_vol_change', 'flow_lg_elg_accel', 'chip_concentration_range', 'chip_skewness', 'floating_chip_proxy', 'cost_support_15pct_change', 'cat_winner_price_zone', 'flow_chip_consistency', 'profit_taking_vs_absorb', 'cat_is_positive', 'upside_vol', 'downside_vol', 'vol_ratio', 'return_skew', 'return_kurtosis', 'volume_change_rate', 'cat_volume_breakout', 'turnover_deviation', 'cat_turnover_spike', 'avg_volume_ratio', 'cat_volume_ratio_breakout', 'vol_spike', 'vol_std_5', 'atr_14', 'atr_6', 'obv', 'maobv_6', 'rsi_3', 'return_5', 'return_20', 'std_return_5', 'std_return_90', 'std_return_90_2', 'act_factor1', 'act_factor2', 'act_factor3', 'act_factor4', 'rank_act_factor1', 'rank_act_factor2', 'rank_act_factor3', 'cov', 'delta_cov', 'alpha_22_improved', 'alpha_003', 'alpha_007', 'alpha_013', 'vol_break', 'weight_roc5', 'price_cost_divergence', 'smallcap_concentration', 'cost_stability', 'high_cost_break_days', 'liquidity_risk', 'turnover_std', 'mv_volatility', 'volume_growth', 'mv_growth', 'momentum_factor', 'resonance_factor', 'log_close', 'cat_vol_spike', 'up', 'down', 'obv_maobv_6', 'std_return_5_over_std_return_90', 'std_return_90_minus_std_return_90_2', 'cat_af2', 'cat_af3', 'cat_af4', 'act_factor5', 'act_factor6', 'active_buy_volume_large', 'active_buy_volume_big', 'active_buy_volume_small', 'buy_lg_vol_minus_sell_lg_vol', 'buy_elg_vol_minus_sell_elg_vol', 'ctrl_strength', 'low_cost_dev', 'asymmetry', 'lock_factor', 'cat_vol_break', 'cost_atr_adj', 'cat_golden_resonance', 'mv_turnover_ratio', 'mv_adjusted_volume', 'mv_weighted_turnover', 'nonlinear_mv_volume', 'mv_volume_ratio', 'mv_momentum', 'lg_flow_mom_corr_20_60', 'lg_flow_accel', 'profit_pressure', 'underwater_resistance', 'cost_conc_std_20', 'profit_decay_20', 'vol_amp_loss_20', 'vol_drop_profit_cnt_5', 'lg_flow_vol_interact_20', 'cost_break_confirm_cnt_5', 'atr_norm_channel_pos_14', 'turnover_diff_skew_20', 'lg_sm_flow_diverge_20', 'pullback_strong_20_20', 'vol_wgt_hist_pos_20', 'vol_adj_roc_20', 'cs_rank_net_lg_flow_val', 'cs_rank_flow_divergence', 'cs_rank_ind_adj_lg_flow', 'cs_rank_elg_buy_ratio', 'cs_rank_rel_profit_margin', 'cs_rank_cost_breadth', 'cs_rank_dist_to_upper_cost', 'cs_rank_winner_rate', 'cs_rank_intraday_range', 'cs_rank_close_pos_in_range', 'cs_rank_opening_gap', 'cs_rank_pos_in_hist_range', 'cs_rank_vol_x_profit_margin', 'cs_rank_lg_flow_price_concordance', 'cs_rank_turnover_per_winner', 'cs_rank_ind_cap_neutral_pe', 'cs_rank_volume_ratio', 'cs_rank_elg_buy_sell_sm_ratio', 'cs_rank_cost_dist_vol_ratio', 'cs_rank_size']\n"
]
@@ -694,7 +722,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 11,
"id": "b87b938028afa206",
"metadata": {
"ExecuteTime": {
@@ -732,7 +760,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 12,
"id": "f4f16d63ad18d1bc",
"metadata": {
"ExecuteTime": {
@@ -958,7 +986,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 13,
"id": "40e6b68a91b30c79",
"metadata": {
"ExecuteTime": {
@@ -1278,7 +1306,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 14,
"id": "47c12bb34062ae7a",
"metadata": {
"ExecuteTime": {
@@ -1312,7 +1340,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 15,
"id": "29221dde",
"metadata": {},
"outputs": [
@@ -1355,7 +1383,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 16,
"id": "03ee5daf",
"metadata": {},
"outputs": [],
@@ -1368,7 +1396,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 17,
"id": "b76ea08a",
"metadata": {},
"outputs": [
@@ -1389,7 +1417,14 @@
"name": "stderr",
"output_type": "stream",
"text": [
"MAD Filtering: 100%|██████████| 131/131 [00:14<00:00, 8.77it/s]\n"
"MAD Filtering: 62%|██████▏ | 81/131 [00:08<00:05, 9.28it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"MAD Filtering: 100%|██████████| 131/131 [00:13<00:00, 9.63it/s]\n"
]
},
{
@@ -1404,14 +1439,7 @@
"name": "stderr",
"output_type": "stream",
"text": [
"MAD Filtering: 82%|████████▏ | 107/131 [00:12<00:02, 9.41it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"MAD Filtering: 100%|██████████| 131/131 [00:13<00:00, 9.60it/s]\n"
"MAD Filtering: 100%|██████████| 131/131 [00:14<00:00, 8.97it/s]\n"
]
},
{
@@ -1451,13 +1479,13 @@
"截面 MAD 去极值处理完成。\n",
"feature_columns: ['vol', 'pct_chg', 'turnover_rate', 'volume_ratio', 'winner_rate', 'undist_profit_ps', 'ocfps', 'AR', 'BR', 'AR_BR', 'cashflow_to_ev_factor', 'book_to_price_ratio', 'turnover_rate_mean_5', 'variance_20', 'bbi_ratio_factor', 'daily_deviation', 'lg_elg_net_buy_vol', 'flow_lg_elg_intensity', 'sm_net_buy_vol', 'total_buy_vol', 'lg_elg_buy_prop', 'flow_struct_buy_change', 'lg_elg_net_buy_vol_change', 'flow_lg_elg_accel', 'chip_concentration_range', 'chip_skewness', 'floating_chip_proxy', 'cost_support_15pct_change', 'cat_winner_price_zone', 'flow_chip_consistency', 'profit_taking_vs_absorb', 'cat_is_positive', 'upside_vol', 'downside_vol', 'vol_ratio', 'return_skew', 'return_kurtosis', 'volume_change_rate', 'cat_volume_breakout', 'turnover_deviation', 'cat_turnover_spike', 'avg_volume_ratio', 'cat_volume_ratio_breakout', 'vol_spike', 'vol_std_5', 'atr_14', 'atr_6', 'obv', 'maobv_6', 'rsi_3', 'return_5', 'return_20', 'std_return_5', 'std_return_90', 'std_return_90_2', 'act_factor1', 'act_factor2', 'act_factor3', 'act_factor4', 'rank_act_factor1', 'rank_act_factor2', 'rank_act_factor3', 'cov', 'delta_cov', 'alpha_22_improved', 'alpha_003', 'alpha_007', 'alpha_013', 'vol_break', 'weight_roc5', 'smallcap_concentration', 'cost_stability', 'high_cost_break_days', 'liquidity_risk', 'turnover_std', 'mv_volatility', 'volume_growth', 'mv_growth', 'momentum_factor', 'resonance_factor', 'log_close', 'cat_vol_spike', 'up', 'down', 'obv_maobv_6', 'std_return_5_over_std_return_90', 'std_return_90_minus_std_return_90_2', 'cat_af2', 'cat_af3', 'cat_af4', 'act_factor5', 'act_factor6', 'active_buy_volume_large', 'active_buy_volume_big', 'active_buy_volume_small', 'buy_lg_vol_minus_sell_lg_vol', 'buy_elg_vol_minus_sell_elg_vol', 'ctrl_strength', 'low_cost_dev', 'asymmetry', 'lock_factor', 'cat_vol_break', 'cost_atr_adj', 'cat_golden_resonance', 'mv_turnover_ratio', 'mv_adjusted_volume', 'mv_weighted_turnover', 'nonlinear_mv_volume', 'mv_volume_ratio', 'mv_momentum', 'lg_flow_mom_corr_20_60', 'lg_flow_accel', 'profit_pressure', 'underwater_resistance', 'cost_conc_std_20', 'profit_decay_20', 'vol_amp_loss_20', 'vol_drop_profit_cnt_5', 'lg_flow_vol_interact_20', 'cost_break_confirm_cnt_5', 'atr_norm_channel_pos_14', 'turnover_diff_skew_20', 'lg_sm_flow_diverge_20', 'pullback_strong_20_20', 'vol_wgt_hist_pos_20', 'vol_adj_roc_20', 'cs_rank_net_lg_flow_val', 'cs_rank_elg_buy_ratio', 'cs_rank_rel_profit_margin', 'cs_rank_cost_breadth', 'cs_rank_dist_to_upper_cost', 'cs_rank_winner_rate', 'cs_rank_intraday_range', 'cs_rank_close_pos_in_range', 'cs_rank_pos_in_hist_range', 'cs_rank_vol_x_profit_margin', 'cs_rank_lg_flow_price_concordance', 'cs_rank_turnover_per_winner', 'cs_rank_volume_ratio', 'cs_rank_elg_buy_sell_sm_ratio', 'cs_rank_cost_dist_vol_ratio', 'cs_rank_size', 'cat_up_limit', 'industry_obv', 'industry_return_5', 'industry_return_20', 'industry__ema_5', 'industry__ema_13', 'industry__ema_20', 'industry__ema_60', 'industry_act_factor1', 'industry_act_factor2', 'industry_act_factor3', 'industry_act_factor4', 'industry_act_factor5', 'industry_act_factor6', 'industry_rank_act_factor1', 'industry_rank_act_factor2', 'industry_rank_act_factor3', 'industry_return_5_percentile', 'industry_return_20_percentile', '000852.SH_MACD', '000905.SH_MACD', '399006.SZ_MACD', '000852.SH_MACD_hist', '000905.SH_MACD_hist', '399006.SZ_MACD_hist', '000852.SH_RSI', '000905.SH_RSI', '399006.SZ_RSI', '000852.SH_Signal_line', '000905.SH_Signal_line', '399006.SZ_Signal_line', '000852.SH_amount_change_rate', '000905.SH_amount_change_rate', '399006.SZ_amount_change_rate', '000852.SH_amount_mean', '000905.SH_amount_mean', '399006.SZ_amount_mean', '000852.SH_daily_return', '000905.SH_daily_return', '399006.SZ_daily_return', '000852.SH_up_ratio_20d', '000905.SH_up_ratio_20d', '399006.SZ_up_ratio_20d', '000852.SH_volatility', '000905.SH_volatility', '399006.SZ_volatility', '000852.SH_volume_change_rate', '000905.SH_volume_change_rate', '399006.SZ_volume_change_rate']\n",
"df最小日期: 2019-01-02\n",
"df最大日期: 2025-10-10\n",
"2056336\n",
"df最大日期: 2025-11-21\n",
"2056030\n",
"train_data最小日期: 2020-01-02\n",
"train_data最大日期: 2022-12-30\n",
"2045675\n",
"2135782\n",
"test_data最小日期: 2023-01-03\n",
"test_data最大日期: 2025-10-10\n",
"test_data最大日期: 2025-11-21\n",
" ts_code trade_date log_circ_mv\n",
"0 000001.SZ 2019-01-02 16.574219\n",
"1 000001.SZ 2019-01-03 16.583965\n",
@@ -1593,7 +1621,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 18,
"id": "3ff2d1c5",
"metadata": {},
"outputs": [],
@@ -1734,14 +1762,14 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 19,
"id": "a5bbb8be",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<catboost.core.CatBoostClassifier at 0x707ccc5ac1a0>"
"<catboost.core.CatBoostClassifier at 0x7602293f6030>"
]
},
"execution_count": 19,
@@ -1759,7 +1787,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 20,
"id": "5d1522a7538db91b",
"metadata": {
"ExecuteTime": {
@@ -1797,7 +1825,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 21,
"id": "09b1799e",
"metadata": {},
"outputs": [
@@ -1819,7 +1847,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 22,
"id": "e53b209a",
"metadata": {},
"outputs": [
@@ -1827,7 +1855,7 @@
"name": "stdout",
"output_type": "stream",
"text": [
"5588 2056336\n",
"5587 2056030\n",
" ts_code trade_date turnover_rate\n",
"0 000001.SZ 2023-01-03 1.1307\n",
"1 000001.SZ 2023-01-04 1.1284\n",
@@ -1835,13 +1863,13 @@
"3 000001.SZ 2023-01-06 0.6162\n",
"4 000001.SZ 2023-01-09 0.5450\n",
"... ... ... ...\n",
"2045670 605599.SH 2025-09-26 0.3434\n",
"2045671 605599.SH 2025-09-29 0.3943\n",
"2045672 605599.SH 2025-09-30 0.4982\n",
"2045673 605599.SH 2025-10-09 1.0319\n",
"2045674 605599.SH 2025-10-10 0.8859\n",
"2135777 605599.SH 2025-11-17 0.3820\n",
"2135778 605599.SH 2025-11-18 0.3565\n",
"2135779 605599.SH 2025-11-19 0.3748\n",
"2135780 605599.SH 2025-11-20 0.3132\n",
"2135781 605599.SH 2025-11-21 0.4580\n",
"\n",
"[2045675 rows x 3 columns]\n"
"[2135782 rows x 3 columns]\n"
]
}
],
@@ -1867,7 +1895,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.13.2"
"version": "3.12.11"
}
},
"nbformat": 4,